Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation

2026-04-29

AI Summary

Existing zero-shot vision-and-language navigation (VLN) approaches often suffer from low success rates due to path deviation and premature termination. This work proposes a three-view navigation protocol grounded in multimodal large language models (MLLMs): a “look-ahead” module extracts global landmarks and generates a coarse plan, a “look-around” module aligns current visual observations with subgoals for fine-grained guidance, and, innovatively, a “look-back” mechanism retrospectively analyzes the traversed trajectory to correct accumulated drift. Notably, the proposed method achieves state-of-the-art zero-shot navigation performance on the R2R-CE and RxR-CE benchmarks without requiring any fine-tuning or gradient updates.

Abstract

Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, current zero-shot Vision-and-Language Navigation (VLN) agents powered by MLLMs still tend to drift off course, halt prematurely, and achieve low overall success rates. We propose Three-Step Nav to counteract these failures with a three-view protocol: First, "look forward" to extract global landmarks and sketch a coarse plan. Then, "look now" to align the current visual observation with the next sub-goal for fine-grained guidance. Finally, "look backward" audits the entire trajectory to correct accumulated drift before stopping. Requiring no gradient updates or task-specific fine-tuning, our planner drops into existing VLN pipelines with minimal overhead. Three-Step Nav achieves state-of-the-art zero-shot performance on the R2R-CE and RxR-CE dataset. Our code is available at https://github.com/ZoeyZheng0/3-step-Nav.

Problem

• Vision-and-Language Navigation
• zero-shot
• navigation drift
• premature halting
• success rate

Innovation

• Three-Step Nav
• zero-shot VLN
• hierarchical planning
• multimodal LLMs
• trajectory correction